Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 939 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 5.0017. Min Range: -5.0017

Max Act: 5.0017. Min Act: -0.1700

Data Index: 321534 (C4 (Web Text))

Max Activating Token Index: 772

Text #1

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.8142. Min Act: -0.1700

Data Index: 1162838 (C4 (Web Text))

Max Activating Token Index: 503

Text #2

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.6892. Min Act: -0.1700

Data Index: 1231980 (C4 (Web Text))

Max Activating Token Index: 169

Text #3

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.6892. Min Act: -0.1700

Data Index: 39861 (C4 (Web Text))

Max Activating Token Index: 344

Text #4

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.6267. Min Act: -0.1700

Data Index: 21390 (C4 (Web Text))

Max Activating Token Index: 764

Text #5

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5642. Min Act: -0.1700

Data Index: 911836 (C4 (Web Text))

Max Activating Token Index: 761

Text #6

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5642. Min Act: -0.1700

Data Index: 677965 (C4 (Web Text))

Max Activating Token Index: 1001

Text #7

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5642. Min Act: -0.1700

Data Index: 731390 (C4 (Web Text))

Max Activating Token Index: 588

Text #8

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5329. Min Act: -0.1700

Data Index: 348987 (C4 (Web Text))

Max Activating Token Index: 965

Text #9

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5642. Min Act: -0.1700

Data Index: 763172 (C4 (Web Text))

Max Activating Token Index: 810

Text #10

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5329. Min Act: -0.1700

Data Index: 147677 (C4 (Web Text))

Max Activating Token Index: 309

Text #11

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5642. Min Act: -0.1700

Data Index: 57988 (C4 (Web Text))

Max Activating Token Index: 122

Text #12

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5017. Min Act: -0.1700

Data Index: 1223848 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5329. Min Act: -0.1700

Data Index: 875491 (C4 (Web Text))

Max Activating Token Index: 652

Text #14

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5017. Min Act: -0.1700

Data Index: 237575 (C4 (Web Text))

Max Activating Token Index: 494

Text #15

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5329. Min Act: -0.1700

Data Index: 365298 (C4 (Web Text))

Max Activating Token Index: 595

Text #16

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.4704. Min Act: -0.1700

Data Index: 390158 (C4 (Web Text))

Max Activating Token Index: 697

Text #17

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.4704. Min Act: -0.1700

Data Index: 983001 (C4 (Web Text))

Max Activating Token Index: 794

Text #18

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5017. Min Act: -0.1700

Data Index: 538420 (C4 (Web Text))

Max Activating Token Index: 232

Text #19

Max Range: 5.0017. Min Range: -5.0017

Max Act: 4.5017. Min Act: -0.1700

Data Index: 51593 (C4 (Web Text))

Max Activating Token Index: 241